https://skillfed.io/news/2026-08-27/annotations-as-rollouts-efficient-and-scalable-reinforcement-learning-for-video SkillFed en 2026-08-27T14:15:08+00:00 Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs https://skillfed.io/news/2026-08-27/autosaddler-automatic-harness-optimization-with-durable-updates-from-agent SkillFed en 2026-08-27T14:15:08+00:00 AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces https://skillfed.io/news/2026-08-27/best-practice-critic-optimization SkillFed en 2026-08-27T14:15:08+00:00 Best Practice Critic Optimization https://skillfed.io/news/2026-08-27/claude-seo SkillFed en 2026-08-27T14:15:08+00:00 AgriciDaniel/claude-seo https://skillfed.io/news/2026-08-27/freellmapi SkillFed en 2026-08-27T14:15:08+00:00 tashfeenahmed/freellmapi https://skillfed.io/news/2026-08-27/gigabrain-0-7-scaling-embodied-foundation-models-to-emergent-capabilities-with SkillFed en 2026-08-27T14:15:08+00:00 GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture https://skillfed.io/news/2026-08-27/jiuwenswarm SkillFed en 2026-08-27T14:15:08+00:00 openJiuwen-ai/jiuwenswarm https://skillfed.io/news/2026-08-27/meta-n-recursive-self-improvement-through-emergent-depth SkillFed en 2026-08-27T14:15:08+00:00 Meta^n: Recursive Self-Improvement through Emergent Depth https://skillfed.io/news/2026-08-27/multica SkillFed en 2026-08-27T14:15:08+00:00 multica-ai/multica https://skillfed.io/news/2026-08-27/on-policy-distillation-with-verifiable-reward SkillFed en 2026-08-27T14:15:08+00:00 On-policy Distillation with Verifiable Reward https://skillfed.io/news/2026-08-27/on-policy-self-distillation-in-diffusion-models SkillFed en 2026-08-27T14:15:08+00:00 On-Policy Self-Distillation in Diffusion Models https://skillfed.io/news/2026-08-27/openhuman SkillFed en 2026-08-27T14:15:08+00:00 tinyhumansai/openhuman https://skillfed.io/news/2026-08-27/openmontage SkillFed en 2026-08-27T14:15:08+00:00 calesthio/OpenMontage https://skillfed.io/news/2026-08-27/paperthin SkillFed en 2026-08-27T14:15:08+00:00 LilMGenius/paperthin https://skillfed.io/news/2026-08-27/rocketride-server SkillFed en 2026-08-27T14:15:08+00:00 rocketride-org/rocketride-server https://skillfed.io/news/2026-08-27/secopd-mitigating-adaptive-prompt-injections-by-on-policy-distillation SkillFed en 2026-08-27T14:15:08+00:00 SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation https://skillfed.io/news/2026-08-27/transformers SkillFed en 2026-08-27T14:15:08+00:00 transformers 5.16.1 https://skillfed.io/news/2026-08-28/agent-g-2-gaussian-guidance-for-agentic-reinforcement-learning SkillFed en 2026-08-28T14:15:08+00:00 Agent-G^2: Gaussian Guidance for Agentic Reinforcement Learning https://skillfed.io/news/2026-08-28/code-world-model-coding-agent-as-world-brain SkillFed en 2026-08-28T14:15:08+00:00 Code World Model: Coding Agent as World Brain https://skillfed.io/news/2026-08-28/creator-buddy SkillFed en 2026-08-28T14:15:08+00:00 SpaceZephyr/creator-buddy https://skillfed.io/news/2026-08-28/frontierchallenge-evaluating-scientific-workflow-completion SkillFed en 2026-08-28T14:15:08+00:00 FrontierChallenge: Evaluating Scientific Workflow Completion https://skillfed.io/news/2026-08-28/instructor SkillFed en 2026-08-28T14:15:08+00:00 instructor 1.16.0 https://skillfed.io/news/2026-08-28/is-next-chunk-reasoning-rl-really-better-than-sft-revisiting-training SkillFed en 2026-08-28T14:15:08+00:00 Is Next-Chunk Reasoning RL Really Better than SFT? Revisiting Training Strategies under no-CoT Data https://skillfed.io/news/2026-08-28/jit-agent-scaling-harness-intelligence-via-just-in-time-harness-evolution SkillFed en 2026-08-28T14:15:08+00:00 JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution https://skillfed.io/news/2026-08-28/jiuwenswarm SkillFed en 2026-08-28T14:15:08+00:00 openJiuwen-ai/jiuwenswarm https://skillfed.io/news/2026-08-28/long-horizon-audio-visual-generation-for-persistent-stories-and-interactive SkillFed en 2026-08-28T14:15:08+00:00 Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds https://skillfed.io/news/2026-08-28/open-mopd-diagnosing-and-fixing-capability-imbalance-in-multi-teacher-on-policy SkillFed en 2026-08-28T14:15:08+00:00 Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation https://skillfed.io/news/2026-08-28/router SkillFed en 2026-08-28T14:15:08+00:00 workweave/router https://skillfed.io/news/2026-08-28/scientific-agent-skills SkillFed en 2026-08-28T14:15:08+00:00 K-Dense-AI/scientific-agent-skills https://skillfed.io/news/2026-08-28/skills SkillFed en 2026-08-28T14:15:08+00:00 jakubkrehel/skills https://skillfed.io/news/2026-08-28/terminal-bench-science SkillFed en 2026-08-28T14:15:08+00:00 harbor-framework/terminal-bench-science https://skillfed.io/news/2026-08-28/vbvr-pro-a-scalable-and-verifiable-suite-for-native-visual-reasoning SkillFed en 2026-08-28T14:15:08+00:00 VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning https://skillfed.io/news/2026-08-28/vgi-bench-probing-visual-intelligence-in-video-generation-models SkillFed en 2026-08-28T14:15:08+00:00 VGI-Bench: Probing Visual Intelligence in Video Generation Models https://skillfed.io/news/2026-08-28/wemm-embedding SkillFed en 2026-08-28T14:15:08+00:00 Tencent/WeMM-Embedding